INDEX
Explanations
references to the concept of beginnings or origins in texts
New Auto-Interp
Negative Logits
esi
-0.15
anced
-0.14
itational
-0.14
fat
-0.14
ãģĭãģĦ
-0.14
ifo
-0.14
alie
-0.14
UTO
-0.14
eder
-0.14
etur
-0.13
POSITIVE LOGITS
/end
0.27
nings
0.23
/start
0.19
-middle
0.18
/Foundation
0.17
isto
0.17
-END
0.17
,end
0.16
-begin
0.16
sek
0.15
Activations Density 0.121%